From fd0d000b2c34aa43d4e92dcf0dfaeda7e123008a Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Mon, 2 Apr 2012 20:19:08 +0200 Subject: perf: Pass last sampling period to perf_sample_data_init() We always need to pass the last sample period to perf_sample_data_init(), otherwise the event distribution will be wrong. Thus, modifiyng the function interface with the required period as argument. So basically a pattern like this: perf_sample_data_init(&data, ~0ULL); data.period = event->hw.last_period; will now be like that: perf_sample_data_init(&data, ~0ULL, event->hw.last_period); Avoids unininitialized data.period and simplifies code. Signed-off-by: Robert Richter Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1333390758-10893-3-git-send-email-robert.richter@amd.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ddbb6a901f65..f32578634d9d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1132,11 +1132,14 @@ struct perf_sample_data { struct perf_branch_stack *br_stack; }; -static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr) +static inline void perf_sample_data_init(struct perf_sample_data *data, + u64 addr, u64 period) { + /* remaining struct members initialized in perf_prepare_sample() */ data->addr = addr; data->raw = NULL; data->br_stack = NULL; + data->period = period; } extern void perf_output_sample(struct perf_output_handle *handle, -- cgit v1.2.3 From cb04ff9ac424d0e689d9b612e9f73cb443ab4b7e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 May 2012 18:56:04 +0200 Subject: sched, perf: Use a single callback into the scheduler We can easily use a single callback for both sched-in and sched-out. This reduces the code footprint in the scheduler path as well as removes the PMU black spot otherwise present between the out and in callback. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-o56ajxp1edwqg6x9d31wb805@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 24 ++++++------------------ 1 file changed, 6 insertions(+), 18 deletions(-) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f32578634d9d..8adf70e9e3cc 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1084,10 +1084,8 @@ extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); extern const char *perf_pmu_name(void); -extern void __perf_event_task_sched_in(struct task_struct *prev, - struct task_struct *task); -extern void __perf_event_task_sched_out(struct task_struct *prev, - struct task_struct *next); +extern void __perf_event_task_sched(struct task_struct *prev, + struct task_struct *next); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); @@ -1207,20 +1205,13 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) extern struct static_key_deferred perf_sched_events; -static inline void perf_event_task_sched_in(struct task_struct *prev, +static inline void perf_event_task_sched(struct task_struct *prev, struct task_struct *task) -{ - if (static_key_false(&perf_sched_events.key)) - __perf_event_task_sched_in(prev, task); -} - -static inline void perf_event_task_sched_out(struct task_struct *prev, - struct task_struct *next) { perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); if (static_key_false(&perf_sched_events.key)) - __perf_event_task_sched_out(prev, next); + __perf_event_task_sched(prev, task); } extern void perf_event_mmap(struct vm_area_struct *vma); @@ -1295,11 +1286,8 @@ extern void perf_event_disable(struct perf_event *event); extern void perf_event_task_tick(void); #else static inline void -perf_event_task_sched_in(struct task_struct *prev, - struct task_struct *task) { } -static inline void -perf_event_task_sched_out(struct task_struct *prev, - struct task_struct *next) { } +perf_event_task_sched(struct task_struct *prev, + struct task_struct *task) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } -- cgit v1.2.3 From ab0cce560ef177bdc7a8f73e9962be9d829a7b2c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 23 May 2012 13:13:02 +0200 Subject: Revert "sched, perf: Use a single callback into the scheduler" This reverts commit cb04ff9ac424 ("sched, perf: Use a single callback into the scheduler"). Before this change was introduced, the process switch worked like this (wrt. to perf event schedule): schedule (prev, next) - schedule out all perf events for prev - switch to next - schedule in all perf events for current (next) After the commit, the process switch looks like: schedule (prev, next) - schedule out all perf events for prev - schedule in all perf events for (next) - switch to next The problem is, that after we schedule perf events in, the pmu is enabled and we can receive events even before we make the switch to next - so "current" still being prev process (event SAMPLE data are filled based on the value of the "current" process). Thats exactly what we see for test__PERF_RECORD test. We receive SAMPLES with PID of the process that our tracee is scheduled from. Discussed with Peter Zijlstra: > Bah!, yeah I guess reverting is the right thing for now. Sad > though. > > So by having the two hooks we have a black-spot between them > where we receive no events at all, this black-spot covers the > hand-over of current and we thus don't receive the 'wrong' > events. > > I rather liked we could do away with both that black-spot and > clean up the code a little, but apparently people rely on it. Signed-off-by: Jiri Olsa Acked-by: Peter Zijlstra Cc: acme@redhat.com Cc: paulus@samba.org Cc: cjashfor@linux.vnet.ibm.com Cc: fweisbec@gmail.com Cc: eranian@google.com Link: http://lkml.kernel.org/r/20120523111302.GC1638@m.brq.redhat.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8adf70e9e3cc..f32578634d9d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1084,8 +1084,10 @@ extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); extern const char *perf_pmu_name(void); -extern void __perf_event_task_sched(struct task_struct *prev, - struct task_struct *next); +extern void __perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task); +extern void __perf_event_task_sched_out(struct task_struct *prev, + struct task_struct *next); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); @@ -1205,13 +1207,20 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) extern struct static_key_deferred perf_sched_events; -static inline void perf_event_task_sched(struct task_struct *prev, +static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) +{ + if (static_key_false(&perf_sched_events.key)) + __perf_event_task_sched_in(prev, task); +} + +static inline void perf_event_task_sched_out(struct task_struct *prev, + struct task_struct *next) { perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); if (static_key_false(&perf_sched_events.key)) - __perf_event_task_sched(prev, task); + __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); @@ -1286,8 +1295,11 @@ extern void perf_event_disable(struct perf_event *event); extern void perf_event_task_tick(void); #else static inline void -perf_event_task_sched(struct task_struct *prev, - struct task_struct *task) { } +perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task) { } +static inline void +perf_event_task_sched_out(struct task_struct *prev, + struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } -- cgit v1.2.3 From 114067b69e7b2c691faace0e33db2f04096f668d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 31 May 2012 14:43:27 +0900 Subject: perf tools: Check if callchain is corrupted We faced segmentation fault on perf top -G at very high sampling rate due to a corrupted callchain. While the root cause was not revealed (I failed to figure it out), this patch tries to protect us from the segfault on such cases. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Sunjin Yang Link: http://lkml.kernel.org/r/1338443007-24857-2-git-send-email-namhyung.kim@lge.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f32578634d9d..1817d4015e5f 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -555,6 +555,8 @@ enum perf_event_type { PERF_RECORD_MAX, /* non-ABI */ }; +#define PERF_MAX_STACK_DEPTH 255 + enum perf_callchain_context { PERF_CONTEXT_HV = (__u64)-32, PERF_CONTEXT_KERNEL = (__u64)-128, @@ -609,8 +611,6 @@ struct perf_guest_info_callbacks { #include #include -#define PERF_MAX_STACK_DEPTH 255 - struct perf_callchain_entry { __u64 nr; __u64 ip[PERF_MAX_STACK_DEPTH]; -- cgit v1.2.3 From 0b0d9cf6ec7bab91977da2d71c09157f110f7c2e Mon Sep 17 00:00:00 2001 From: Arun Sharma Date: Fri, 20 Apr 2012 15:41:34 -0700 Subject: perf: Limit callchains to 127 Stack depth of 255 seems excessive, given that copy_from_user_nmi() could be slow. Signed-off-by: Arun Sharma Cc: Linus Torvalds Cc: linux-kernel@vger.kernel.org Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1334961696-19580-3-git-send-email-asharma@fb.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1817d4015e5f..45db49f64bb4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -555,7 +555,7 @@ enum perf_event_type { PERF_RECORD_MAX, /* non-ABI */ }; -#define PERF_MAX_STACK_DEPTH 255 +#define PERF_MAX_STACK_DEPTH 127 enum perf_callchain_context { PERF_CONTEXT_HV = (__u64)-32, -- cgit v1.2.3